ajarbot/docs/WINDOWS_DEPLOYMENT.md

Windows 11 Deployment Guide

Complete guide for deploying and testing Ajarbot on Windows 11.

Prerequisites

1. Install Python

Download and install Python 3.8 or higher from python.org:

# Verify installation
python --version
# Should show: Python 3.8+

# Verify pip
pip --version

Important: During installation, check "Add Python to PATH"

2. Get API Keys

You'll need at least one of these:

Claude (Anthropic) - Recommended

1. Go to https://console.anthropic.com/
2. Create account or sign in
3. Navigate to API Keys
4. Create new key
5. Copy the key (starts with sk-ant-)

GLM (z.ai) - Optional

1. Go to https://z.ai
2. Sign up and get API key

Quick Start (5 Minutes)

1. Clone or Navigate to Project

# If you haven't already
cd c:\Users\fam1n\projects\ajarbot

2. Create Virtual Environment (Recommended)

# Create virtual environment
python -m venv venv

# Activate it
.\venv\Scripts\activate

# You should see (venv) in your prompt

3. Install Dependencies

pip install -r requirements.txt

Expected output:

Successfully installed anthropic-0.40.0 requests-2.31.0 watchdog-3.0.0 ...

4. Set Environment Variables

Option A: PowerShell (temporary - current session only)

$env:ANTHROPIC_API_KEY = "sk-ant-your-key-here"

# Optional: GLM
$env:GLM_API_KEY = "your-glm-key-here"

Option B: System Environment Variables (persistent)

1. Press Win + X → System
2. Click "Advanced system settings"
3. Click "Environment Variables"
4. Under "User variables", click "New"
5. Variable name: ANTHROPIC_API_KEY
6. Variable value: sk-ant-your-key-here
7. Click OK

Option C: .env file (recommended for development)

# Create .env file in project root
notepad .env

Add to .env:

ANTHROPIC_API_KEY=sk-ant-your-key-here
GLM_API_KEY=your-glm-key-here

Then install python-dotenv and load it:

pip install python-dotenv

5. Test Basic Agent

python example_usage.py

Expected output:

============================================================
Basic Agent Usage Example
============================================================

[Setup] Initializing agent with Claude...
[Setup] Agent initialized

[Test 1] Basic chat...
Agent: [Response from Claude]

[Test 2] Memory operations...
...

Running Different Examples

Basic Agent with Memory

python example_usage.py

What it does:

• Creates agent with Claude
• Tests basic chat
• Demonstrates memory operations
• Shows task management

Pulse & Brain Monitoring

python example_bot_with_pulse_brain.py

What it does:

• Runs cost-effective monitoring
• Pure Python checks (zero cost)
• Conditional AI calls (only when needed)
• Shows real-time status

Press Ctrl+C to stop

Task Scheduler

python example_bot_with_scheduler.py

What it does:

• Schedules recurring tasks
• Demonstrates cron-like syntax
• Shows task execution
• Runs in background

Press Ctrl+C to stop

Skills Integration

python example_bot_with_skills.py

What it does:

• Loads Claude Code skills
• Allows skill invocation
• Demonstrates preprocessing
• Shows available skills

Multi-Platform Bot (Slack + Telegram)

First, generate configuration:

python bot_runner.py --init

This creates config\adapters.local.yaml

Edit the file:

notepad config\adapters.local.yaml

Add your credentials:

adapters:
  slack:
    enabled: true
    credentials:
      bot_token: "xoxb-your-token"
      app_token: "xapp-your-token"

  telegram:
    enabled: true
    credentials:
      bot_token: "your-bot-token"

Run the bot:

python bot_runner.py

Testing Components

Test Skills System

python test_skills.py

Verifies:

• Skill discovery
• Skill loading
• Preprocessor functionality

Test Scheduler

python test_scheduler.py

Verifies:

• Task scheduling
• Schedule parsing
• Task execution

Running as Windows Service (Production)

Option 1: NSSM (Non-Sucking Service Manager)

Install NSSM:

1. Download from https://nssm.cc/download
2. Extract to C:\nssm
3. Add to PATH or use full path

Create Service:

# Run as Administrator
nssm install Ajarbot "C:\Users\fam1n\projects\ajarbot\venv\Scripts\python.exe"

# Set parameters
nssm set Ajarbot AppParameters "bot_runner.py"
nssm set Ajarbot AppDirectory "C:\Users\fam1n\projects\ajarbot"

# Set environment variables
nssm set Ajarbot AppEnvironmentExtra ANTHROPIC_API_KEY=sk-ant-your-key

# Start service
nssm start Ajarbot

Manage Service:

# Check status
nssm status Ajarbot

# Stop service
nssm stop Ajarbot

# Remove service
nssm remove Ajarbot confirm

Option 2: Task Scheduler (Simpler)

Create scheduled task:

1. Open Task Scheduler (Win + R → taskschd.msc)
2. Create Basic Task
3. Name: "Ajarbot"
4. Trigger: "When computer starts"
5. Action: "Start a program"
6. Program: C:\Users\fam1n\projects\ajarbot\venv\Scripts\python.exe
7. Arguments: bot_runner.py
8. Start in: C:\Users\fam1n\projects\ajarbot
9. Finish

Configure task:

• Right-click task → Properties
• Check "Run whether user is logged on or not"
• Check "Run with highest privileges"
• Triggers tab → Edit → Check "Enabled"

Option 3: Simple Startup Script

Create start_ajarbot.bat:

@echo off
cd /d C:\Users\fam1n\projects\ajarbot
call venv\Scripts\activate
set ANTHROPIC_API_KEY=sk-ant-your-key-here
python bot_runner.py
pause

Add to startup:

1. Press Win + R
2. Type shell:startup
3. Copy start_ajarbot.bat to the folder

Running in Background

Using PowerShell

# Start in background
Start-Process python -ArgumentList "bot_runner.py" -WindowStyle Hidden -WorkingDirectory "C:\Users\fam1n\projects\ajarbot"

# Find process
Get-Process python | Where-Object {$_.CommandLine -like "*bot_runner*"}

# Stop process (get PID first)
Stop-Process -Id <PID>

Using pythonw (No console window)

# Run without console window
pythonw bot_runner.py

Monitoring and Logs

View Logs

By default, Python prints to console. To save logs:

Option 1: Redirect to file

python bot_runner.py > logs\bot.log 2>&1

Option 2: Add logging to code

Create config\logging_config.py:

import logging
from pathlib import Path

log_dir = Path("logs")
log_dir.mkdir(exist_ok=True)

logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    handlers=[
        logging.FileHandler(log_dir / "ajarbot.log"),
        logging.StreamHandler()
    ]
)

Then in your scripts:

import logging
logger = logging.getLogger(__name__)
logger.info("Bot started")

Monitor Process

Task Manager:

1. Press Ctrl + Shift + Esc
2. Details tab
3. Find python.exe
4. Check CPU/Memory usage

PowerShell:

# Monitor in real-time
while ($true) {
    Get-Process python | Select-Object CPU, PM, StartTime
    Start-Sleep 5
}

Troubleshooting

"Python is not recognized"

Fix:

1. Find Python installation: C:\Users\fam1n\AppData\Local\Programs\Python\Python3XX
2. Add to PATH:
   • Win + X → System → Advanced → Environment Variables
   • Edit PATH, add Python directory
   • Add Scripts directory too

"Module not found" errors

# Ensure virtual environment is activated
.\venv\Scripts\activate

# Reinstall dependencies
pip install -r requirements.txt --force-reinstall

"API key not found"

Verify environment variable:

# Check if set
$env:ANTHROPIC_API_KEY

# Should show your key, not empty

If empty, set it again:

$env:ANTHROPIC_API_KEY = "sk-ant-your-key"

Port already in use (for adapters)

If running multiple instances:

# Find process using port
netstat -ano | findstr :PORT_NUMBER

# Kill process
taskkill /PID <PID> /F

Memory workspace errors

# Delete and recreate
Remove-Item -Recurse -Force memory_workspace
python example_usage.py

Firewall blocking (for Slack/Telegram)

1. Windows Security → Firewall & network protection
2. Allow an app through firewall
3. Add Python
4. Check both Private and Public

Performance Tips

1. Use SSD for memory_workspace

If you have multiple drives, store memory on SSD:

# In agent.py, modify workspace_path
workspace_path = "D:\fast_storage\ajarbot_memory"

2. Optimize Pulse Interval

For lower CPU usage:

pb = PulseBrain(agent, pulse_interval=300)  # 5 minutes instead of 60 seconds

3. Limit Memory Database Size

# In memory_system.py, add retention policy
memory.cleanup_old_entries(days=30)

4. Run with pythonw

# Lower priority, no console
pythonw bot_runner.py

Security Considerations

1. Protect API Keys

Never commit .env or adapters.local.yaml:

# Check .gitignore includes:
echo ".env" >> .gitignore
echo "config/*.local.yaml" >> .gitignore

2. Use Windows Credential Manager

Store API keys securely:

import keyring

# Store key
keyring.set_password("ajarbot", "anthropic_key", "sk-ant-...")

# Retrieve key
api_key = keyring.get_password("ajarbot", "anthropic_key")

Install keyring:

pip install keyring

3. Run with Limited User

Create dedicated user account:

1. Settings → Accounts → Family & other users
2. Add account → "Ajarbot Service"
3. Run service as this user (limited permissions)

Development Workflow

1. Development Mode

# Activate venv
.\venv\Scripts\activate

# Run with auto-reload (install watchdog)
pip install watchdog[watchmedo]

# Monitor and restart on changes
watchmedo auto-restart --directory=. --pattern=*.py --recursive -- python bot_runner.py

2. Testing Changes

# Quick syntax check
python -m py_compile agent.py

# Run tests
python test_skills.py
python test_scheduler.py

3. Code Formatting

# Install black
pip install black

# Format code
black .

Next Steps

1. Test locally: Run example_usage.py to verify setup
2. Configure adapters: Set up Slack or Telegram
3. Customize: Edit pulse checks, schedules, or skills
4. Deploy: Choose service option (NSSM, Task Scheduler, or Startup)
5. Monitor: Check logs and system resources

Quick Reference

Start Bot

.\venv\Scripts\activate
python bot_runner.py

Stop Bot

Ctrl + C

View Logs

type logs\bot.log

Check Status

python bot_runner.py --health

Update Dependencies

pip install -r requirements.txt --upgrade

---

Need Help?

• Check main documentation
• Review troubleshooting section
• Check Windows Event Viewer for service errors
• Run examples to isolate issues